跳到主要內容

臺灣博碩士論文加值系統

(44.211.31.134) 您好!臺灣時間:2024/07/23 07:57
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:鄒宗霖
研究生(外文):Tsung-Lin Tsou
論文名稱:弱標籤引導的自訓練方法用於弱監督領域自適應三維物體檢測
論文名稱(外文):WLST: Weak Labels Guided Self-training for Weakly-supervised Domain Adaptation on 3D Object Detection
指導教授:徐宏民
指導教授(外文):Winston H. Hsu
口試委員:陳文進陳奕廷葉梅珍
口試委員(外文):Wen-Chin ChenYi-Ting ChenMei-Chen Yeh
口試日期:2023-07-07
學位類別:碩士
校院名稱:國立臺灣大學
系所名稱:資訊工程學系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2023
畢業學年度:111
論文頁數:38
中文關鍵詞:深度學習三維物體檢測領域自適應弱監督領域自適應自訓練方法
外文關鍵詞:Deep Learning3D Object DetectionDomain AdaptationWeakly-supervised Domain AdaptationSelf-training
DOI:10.6342/NTU202301286
相關次數:
  • 被引用被引用:0
  • 點閱點閱:70
  • 評分評分:
  • 下載下載:16
  • 收藏至我的研究室書目清單書目收藏:0
在領域自適應三維物體檢測中,大部分的研究都專注於無監督領域自適應。然而,在缺乏任何目標領域的標註資訊下,無監督領域自適應的方法與在目標領域中完全監督的方法之間仍存在著明顯的性能差距,這對於現實世界的應用來說是不切實際的。另一方面,弱監督領域自適應是一個很少被研究但具有實際應用價值的任務,因為他只需要在目標領域進行少量的標註工作。為了以經濟有效的方式來提高領域自適應性能,我們提出了一個專門為弱監督領域自適應三維物體檢測設計的 WLST 框架,同時他也是一個通用的弱標籤引導的自訓練方法。透過將自動標註器整合進現有的自訓練流程中,該方法能夠生成更穩健且更一致的偽標籤,這將有助於後續在目標領域上的訓練。此外,大量的實驗證實了我們 WLST 框架的有效性、穩健性和對檢測器的獨立性。值得注意的是,他在所有領域自適應的任務上表現都優於先前最先進的方法。
In the field of domain adaptation (DA) on 3D object detection, most of the work is dedicated to unsupervised domain adaptation (UDA). Yet, without any target annotations, the performance gap between the UDA approaches and the fully-supervised approach is still noticeable, which is impractical for real-world applications. On the other hand, weakly-supervised domain adaptation (WDA) is an underexplored yet practical task that only requires few labeling effort on the target domain. To improve the DA performance in a cost-effective way, we propose a general weak labels guided self-training framework, WLST, designed for WDA on 3D object detection. By incorporating autolabeler, which can generate 3D pseudo labels from 2D bounding boxes, into the existing self-training pipeline, our method is able to generate more robust and consistent pseudo labels that would benefit the training process on the target domain. Extensive experiments demonstrate the effectiveness, robustness, and detector-agnosticism of our WLST framework. Notably, it outperforms previous state-of-the-art methods on all evaluation tasks.
Verification Letter from the Oral Examination Committee i
摘要 iii
Abstract v
Contents vii
List of Figures ix
List of Tables xi
Chapter 1 Introduction 1
Chapter 2 Related Work 5
Chapter 3 Methodology 7
3.1 Problem Formulation 7
3.2 Weak Labels Guided Selftraining Framework 8
3.2.1 Autolabeler 8
3.2.2 Model Pretraining 10
3.2.3 Pseudolabel Generation 11
3.2.4 Model Retraining 14
Chapter 4 Experiments 15
4.1 Experiment settings 15
4.2 Experiment Results 17
4.3 Ablation Studies 19
Chapter 5 Conclusion 23
References 25
Appendix A — Implementation Details 31
A.1 Parameter Setups 31
A.2 Implementation Details of Autolabeler 31
Appendix B — More Experiment Results 35
B.1 Autolabeleragnostic Analysis 35
B.2 Experiment Results at IoU = 0.5 37
B.3 Comparing to weaklysupervised 3D object detection methods 37
H. Caesar, V. Bankiti, A. H. Lang, S. Vora, V. E. Liong, Q. Xu, A. Krishnan, Y. Pan, G. Baldan, and O. Beijbom. nuscenes: A multimodal dataset for autonomous driving. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 11621–11631, 2020.
Z. Cai and N. Vasconcelos. Cascade rcnn: Delving into high quality object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 6154–6162, 2018.
Y.T. Chen, J. Shi, Z. Ye, C. Mertz, D. Ramanan, and S. Kong. Multimodal object detection via probabilistic ensembling. In Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part IX, pages 139–158. Springer, 2022.
J. Deng, S. Shi, P. Li, W. Zhou, Y. Zhang, and H. Li. Voxel rcnn: Towards high performance voxelbased 3d object detection. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 1201–1209, 2021.
R. Ge, Z. Ding, Y. Hu, Y. Wang, S. Chen, L. Huang, and Y. Li. Afdet: Anchor free one stage 3d object detection. arXiv preprint arXiv:2006.12671, 2020.
A. Geiger, P. Lenz, and R. Urtasun. Are we ready for autonomous driving? the kitti vision benchmark suite. In 2012 IEEE conference on computer vision and pattern recognition, pages 3354–3361. IEEE, 2012.
D. P. Kingma and J. Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
A. H. Lang, S. Vora, H. Caesar, L. Zhou, J. Yang, and O. Beijbom. Pointpillars: Fast encoders for object detection from point clouds. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 12697–12705, 2019.
C. Liu, X. Qian, X. Qi, E. Y. Lam, S.C. Tan, and N. Wong. Mapgen: An automated 3dbox annotation flow with multimodal attention point generator. In 2022 26th International Conference on Pattern Recognition (ICPR), pages 1148–1155. IEEE, 2022.
Z. Luo, Z. Cai, C. Zhou, G. Zhang, H. Zhao, S. Yi, S. Lu, H. Li, S. Zhang, and Z. Liu. Unsupervised domain adaptive 3d detection with multilevel consistency. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 8866–8875, 2021.
Q. Meng, W. Wang, T. Zhou, J. Shen, Y. Jia, and L. Van Gool. Towards a weakly supervised framework for 3d point cloud object detection and annotation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(8):4454–4468, 2021.
Q. Meng, W. Wang, T. Zhou, J. Shen, L. Van Gool, and D. Dai. Weakly supervised 3d object detection from lidar point cloud. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XIII, pages 515–531. Springer, 2020.
S. Pang, D. Morris, and H. Radha. Clocs: Cameralidar object candidates fusion for 3d object detection. In 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 10386–10393. IEEE, 2020.
C. R. Qi, W. Liu, C. Wu, H. Su, and L. J. Guibas. Frustum pointnets for 3d object detection from rgbd data. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 918–927, 2018.
C. R. Qi, H. Su, K. Mo, and L. J. Guibas. Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 652–660, 2017.
C. R. Qi, L. Yi, H. Su, and L. J. Guibas. Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems, 30, 2017.
S. Shi, C. Guo, L. Jiang, Z. Wang, J. Shi, X. Wang, and H. Li. Pvrcnn: Pointvoxel feature set abstraction for 3d object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10529–10538, 2020.
S. Shi, L. Jiang, J. Deng, Z. Wang, C. Guo, J. Shi, X. Wang, and H. Li. Pvrcnn++: Pointvoxel feature set abstraction with local vector representation for 3d object detection. International Journal of Computer Vision, pages 1–21, 2022.
S. Shi, X. Wang, and H. Li. Pointrcnn: 3d object proposal generation and detection from point cloud. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 770–779, 2019.
S. Shi, Z. Wang, J. Shi, X. Wang, and H. Li. From points to parts: 3d object detection from point cloud with partaware and partaggregation network. IEEE transactions on pattern analysis and machine intelligence, 43(8):2647–2664, 2020.
P. Sun, H. Kretzschmar, X. Dotiwalla, A. Chouard, V. Patnaik, P. Tsui, J. Guo, Y. Zhou, Y. Chai, B. Caine, et al. Scalability in perception for autonomous driving: Waymo open dataset. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 2446–2454, 2020.
Y. S. Tang and G. H. Lee. Transferable semisupervised 3d object detection from rgbd data. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 1931–1940, 2019.
O. D. Team. Openpcdet: An opensource toolbox for 3d object detection from point clouds. https://github.com/open mmlab/OpenPCDet, 2020.
Y. Wang, X. Chen, Y. You, L. E. Li, B. Hariharan, M. Campbell, K. Q. Weinberger, and W.L. Chao. Train in germany, test in the usa: Making 3d object detectors generalize. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11713–11723, 2020.
Y. Wei, S. Su, J. Lu, and J. Zhou. Fgr: Frustumaware geometric reasoning for weakly supervised 3d vehicle detection. In 2021 IEEE International Conference on Robotics and Automation (ICRA), pages 4348–4354. IEEE, 2021.
Y. Yan, Y. Mao, and B. Li. Second: Sparsely embedded convolutional detection. Sensors, 18(10):3337, 2018.
J. Yang, S. Shi, Z. Wang, H. Li, and X. Qi. St3d: Selftraining for unsupervised domain adaptation on 3d object detection. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10368–10378, 2021.
J. Yang, S. Shi, Z. Wang, H. Li, and X. Qi. St3d++: denoised selftraining for unsupervised domain adaptation on 3d object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022.
Z. Yang, Y. Sun, S. Liu, X. Shen, and J. Jia. Std: Sparsetodense 3d object detector for point cloud. In Proceedings of the IEEE/CVF international conference on computer vision, pages 1951–1960, 2019.
T. Yin, X. Zhou, and P. Krahenbuhl. Centerbased 3d object detection and tracking. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 11784–11793, 2021.
Y. You, C. A. DiazRuiz, Y. Wang, W.L. Chao, B. Hariharan, M. Campbell, and K. Q. Weinbergert. Exploiting playbacks in unsupervised domain adaptation for 3d object detection in selfdriving cars. In 2022 International Conference on Robotics and Automation (ICRA), pages 5070–5077. IEEE, 2022.
W. Zheng, W. Tang, S. Chen, L. Jiang, and C.W. Fu. Ciassd: Confident iou aware singlestage object detector from point cloud. In Proceedings of the AAAI conference on artificial intelligence, volume 35, pages 3555–3562, 2021.
Y. Zhou and O. Tuzel. Voxelnet: Endtoend learning for point cloud based 3d object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4490–4499, 2018.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊